Playing with any large language model (LLM), such as GPT-4, is fascinating. But it doesn’t give you an accurate understanding of where AGI is heading because one isolated snapshot provides limited information. You can gain more insight into the growth and dynamicity of LLMs by comparing two subsequent snapshots. Roughly speaking, it’s less interesting to … Read more
💡 Info: I haven’t used any affiliate links in this list, so you know there’s no bias. If you want to boost your ChatGPT skills, feel free to download our ChatGPT cheat sheet for free here. 👇 Download PDF Prompting Cheat Sheet (ChatGPT) If you want more cheat sheets and be on the right side … Read more
Prompt injection is a technique that can hijack a language model’s output by using untrusted text as part of the prompt. Similar to other injection attacks in the information security field, prompt injection can occur when instructions and data are concatenated, making it difficult for the underlying engine to distinguish between them (NCC Group Research). … Read more
Are you tired of going to chat.openai.com only to see that ChatGPT is currently overused? Wouldn’t it be great if you could use ChatGPT on your computer, locally, and without Internet access — even if you’re stranded on a remote island? 🏝️ Wouldn’t it be great if you could download a mega brain trained on … Read more
OpenAI’s GPT-4 has taken the world by storm, showing significant advancements over its predecessor, GPT-3.5. As a cutting-edge language model, it boasts an array of new capabilities and improvements, ranging from enhanced understanding of complex prompts to the ability to process visual inputs. One notable achievement of GPT-4 is its ability to score high on … Read more
I was just reading a new research paper from OpenAI researchers proposing that the model accuracy improves if you append “Let’s think step by step” to your prompt: They used a two-step prompting strategy to automatically insert it so the user doesn’t recognize: But we can do it explicitly in our own prompts to try … Read more
Anything new about ChatGPT this week (end of March 2023)? Not much. Only these 50 stories… 🤯 👉 Recommended: Free Download ChatGPT Prompting Cheat Sheet Petition Against AI Research Some big-time celebs (🤩Musk, Wozniak, and more) have signed a petition📝 to put a hold on the development of AI systems stronger than GPT-4. I’m really … Read more
I set out to create a sci-fi story book and this is the first story book that I have ever compiled. I wanted the story to be suggested to me by ChatGPT with the following requirements: The story can be based on Interstellar, like a sequel to it. The story has to be gripping, interesting, … Read more
As human coders, we need to adapt or die. When Google released its powerful search capabilities a couple of decades ago, we needed to learn their search interface or become irrelevant. Because a coder capable of using search effectively is 10x more productive than one who doesn’t. The same holds for large language models (LLMs), … Read more
ChatGPT will disrupt millions of jobs due to increased efficiency, cost savings, scalability, 24/7 availability, instant response, language support, human error reduction, reliable data handling, personalized customer experiences, and routine task automation. It cannot (yet) disrupt all jobs due to its lack of human emotion, privacy concerns, dependency on technology, reduced creativity, job losses, misunderstandings … Read more
I wanted to learn how to read from the text of the US Army field manual and build a chatbot to answer questions from it. The military is embracing ChatBots, so there is demand for a question and answer Chatbots that can give them their operational data at their fingertips. They want to use their … Read more
Hallucinations in the AI context refer to AI-generated experiences, like text or images, that do not correspond to real-world input, leading to potentially false perceptions and misleading results for users. The term was coined in a 2018 ICLR paper written by Google’s AI Research group: 💡 Hallucinations in Neural Machine Translation – Agarwal et al. … Read more